Deep Learning on Traffic Prediction: Methods, Analysis and Future Directions

被引:210
作者
Yin, Xueyan [1 ]
Wu, Genze [1 ]
Wei, Jinze [1 ]
Shen, Yanming [1 ,2 ]
Qi, Heng [1 ]
Yin, Baocai [1 ,3 ]
机构
[1] Dalian Univ Technol, Sch Elect Informat & Elect Engn, Dalian 116024, Peoples R China
[2] Dalian Univ Technol, Minist Educ, Key Lab Intelligent Control & Optimizat Ind Equip, Dalian 116024, Peoples R China
[3] Peng Cheng Lab, Shenzhen 518055, Peoples R China
基金
中国国家自然科学基金;
关键词
Deep learning; Correlation; Predictive models; Data models; Convolution; Roads; Learning systems; Traffic prediction; deep learning; spatial-temporal dependency modeling; CONVOLUTIONAL NEURAL-NETWORKS; FLOW PREDICTION; PASSENGER FLOW; DEMAND; FRAMEWORK; REPRESENTATIONS; REGRESSION;
D O I
10.1109/TITS.2021.3054840
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Traffic prediction plays an essential role in intelligent transportation system. Accurate traffic prediction can assist route planing, guide vehicle dispatching, and mitigate traffic congestion. This problem is challenging due to the complicated and dynamic spatio-temporal dependencies between different regions in the road network. Recently, a significant amount of research efforts have been devoted to this area, especially deep learning method, greatly advancing traffic prediction abilities. The purpose of this paper is to provide a comprehensive survey on deep learning-based approaches in traffic prediction from multiple perspectives. Specifically, we first summarize the existing traffic prediction methods, and give a taxonomy. Second, we list the state-of-the-art approaches in different traffic prediction applications. Third, we comprehensively collect and organize widely used public datasets in the existing literature to facilitate other researchers. Furthermore, we give an evaluation and analysis by conducting extensive experiments to compare the performance of different methods on a real-world public dataset. Finally, we discuss open challenges in this field.
引用
收藏
页码:4927 / 4943
页数:17
相关论文
共 127 条
  • [1] AMAP Technology, 2019, AMAP TECHN ANN 2019
  • [2] Bahdanau D, 2016, Arxiv, DOI arXiv:1409.0473
  • [3] Bai L, 2020, ADV NEUR IN, V33
  • [4] Bai L, 2019, PROCEEDINGS OF THE TWENTY-EIGHTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, P1981
  • [5] Machine Learning-based traffic prediction models for Intelligent Transportation Systems
    Boukerche, Azzedine
    Wang, Jiahao
    [J]. COMPUTER NETWORKS, 2020, 181
  • [6] Bruna J, 2013, ARXIV
  • [7] Bike Flow Prediction with Multi-Graph Convolutional Networks
    Chai, Di
    Wang, Leye
    Yang, Qiang
    [J]. 26TH ACM SIGSPATIAL INTERNATIONAL CONFERENCE ON ADVANCES IN GEOGRAPHIC INFORMATION SYSTEMS (ACM SIGSPATIAL GIS 2018), 2018, : 397 - 400
  • [8] Chen C, 2019, AAAI CONF ARTIF INTE, P485
  • [9] Forecasting holiday daily tourist flow based on seasonal support vector regression with adaptive genetic algorithm
    Chen, Rong
    Liang, Chang-Yong
    Hong, Wei-Chiang
    Gu, Dong-Xiao
    [J]. APPLIED SOFT COMPUTING, 2015, 26 : 435 - 443
  • [10] Chen WQ, 2020, AAAI CONF ARTIF INTE, V34, P3529